파일
rocm-systems/tests/workloads/dev01p3/mi100/SQ_INST_LEVEL_SMEM.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

43 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_SMEMSQ_INST_LEVEL_SMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000931481931486335544322560083264640x00x7f07d2e041804194304325636841667508012076535482203595120765357266039161207653572692823512076535727038578
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00293148193148632768256002424124800x00x7f07d2e3510051223210295574412076535741499958120765357418009041207653574180698412076535741811928
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0049314819314864194304256002424129280x7f0902d9c9000x7f07d2e35140655361756922241932812076535741871739120765357421005831207653574223770212076535742241807
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0069314819314864194304256003624136320x7f0902d9c8000x7f07d2e35180655361644762097774412076535742309664120765357424863421207653574273818112076535742807600
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0089314819314864194304256002824140800x7f0902d9c7000x7f07d2e351c0655361801042294438412076535742840461120765357430324201207653574328777912076535743355419
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00109314819314864194304256002424145280x7f0902d9c6000x7f07d2e35200655361861502382216812076535743380976120765357435664981207653574370473812076535743708085
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00129314819314864194304256002424149760x7f0902d9c5000x7f07d2e35240655362029202596470412076535743757837120765357439292171207653574406841612076535744072142
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00149314819314864194304256002424154240x7f0902d9c4000x7f07d2e352801310722482943171316012076535744153914120765357443261751207653574445609512076535744459463
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00169314819314864194304256002824161280x7f0902d9c3000x7f07d2e352c01310722341562996061612076535744506951120765357446815341207653574493849312076535744980792
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00189314819314864194304256002824168320x7f0902d9ca000x7f07d2e35300655361782142273121612076535745014104120765357451954521207653574544889212076535745491362
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00209314819314864194304256002424175360x7f0902d9c9000x7f07d2e353401310722517783208498412076535745515838120765357457050511207653574583641012076535745839920
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00229314819314864194304256002424182400x7f0902d9c8000x7f07d2e353801310722460283159687212076535745888080120765357460605701207653574619352912076535746197185
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00249314819314864194304256002424189440x7f0902d9c7000x7f07d2e353c01310722738863493625612076535746260092120765357464256881207653574655736812076535746560791
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00269314819314864194304256002824199040x7f0902d9c6000x7f07d2e354001310722041342615358412076535746610524120765357467812071207653574703176612076535747100595
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00289314819314864194304256002824206080x7f0902d9c5000x7f07d2e35440655361705042188292812076535747128638120765357473133651207653574756856512076535747637744
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00309314819314864194304256002424213120x7f0902d9c4000x7f07d2e354801310722493163183112812076535747666298120765357478442441207653574797896312076535747982426
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00329314819314864194304256002424220160x7f0902d9c3000x7f07d2e354c01310722456383144346412076535748034513120765357482112821207653574834520212076535748348607
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00349314819314864194304256002424227200x7f0902d9ca000x7f07d2e355001310722804863586725612076535748408689120765357485709611207653574870232112076535748705841
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00369314819314864194304256002824236800x7f0902d9c9000x7f07d2e355401310722140982740286412076535748755544120765357489173601207653574917447912076535749242960
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00389314819314864194304256002824243840x7f0902d9c8000x7f07d2e35580655361835122347498412076535749279118120765357494629581207653574971527712076535749783957
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00409314819314864194304256002424250880x7f0902d9c7000x7f07d2e355c01310722540323261492012076535749814223120765357499954361207653575012727612076535750130992
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00429314819314864194304256002424257920x7f0902d9c6000x7f07d2e356001310722516243207086412076535750184021120765357503525551207653575048295512076535750486604
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00449314819314864194304256002424264960x7f0902d9c5000x7f07d2e356401310722442623135999212076535750547497120765357507093541207653575084055412076535750843848
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00469314819314864194304256002824277120x7f0902d9c4000x7f07d2e356801310722077542660672812076535750892499120765357510613531207653575131847212076535751387640
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00489314819314864194304256002824284160x7f0902d9c3000x7f07d2e356c0655361643602093108812076535751415181120765357515935111207653575184887012076535751916353
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00509314819314864194304256002424291200x7f0902d9ca000x7f07d2e357001310722467363161617612076535751941921120765357521247091207653575225574912076535752259461
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00529314819314864194304256002424300800x7f0902d9c9000x7f07d2e357401310722478263184821612076535752310176120765357524739881207653575260678812076535752610204
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00549314819314864194304256002424307840x7f0902d9c8000x7f07d2e357801310722437603142697612076535752670346120765357528306271207653575296422612076535752967719
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00569314819314864194304256002824320000x7f0902d9c7000x7f07d2e357c01310722127922718944812076535753022020120765357532043861207653575346342512076535753530947
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00589314819314864194304256002824329600x7f0902d9c6000x7f07d2e35800655361745582232516812076535753555212120765357537341441207653575398502312076535754054691
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00609314819314864194304256002424339200x7f0902d9c5000x7f07d2e358401310722456563149071212076535754082643120765357542599021207653575439494212076535754398460
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00629314819314864194304256002424348800x7f0902d9c4000x7f07d2e358801310722462703148192012076535754446980120765357546087011207653575474326012076535754746718
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00649314819314864194304256002424358400x7f0902d9c3000x7f07d2e358c01310722530103238609612076535754808172120765357549698201207653575509909912076535755102971
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00669314819314864194304256002824373120x7f0902d9ca000x7f07d2e359001310722072182666565612076535755152102120765357553194181207653575557989812076535755647163
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00689314819314864194304256002824382720x7f0902d9c9000x7f07d2e35940655361976182533761612076535755669585120765357558501371207653575610357612076535756171318
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00709314819314864194304256002424392320x7f0902d9c8000x7f07d2e359801310722512103228604012076535756198038120765357563781351207653575650709412076535756510429
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00729314819314864194304256002424401920x7f0902d9c7000x7f07d2e359c01310722541243247414412076535756559220120765357567253341207653575685733312076535756860710
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00749314819314864194304256002424411520x7f0902d9c6000x7f07d2e35a001310722597183316416012076535756921513120765357570867731207653575721925212076535757222784
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00769314819314864194304256002824426240x7f0902d9c5000x7f07d2e35a401310722126622717411212076535757271565120765357574418111207653575769733012076535757763439
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00789314819314864194304256002824435840x7f0902d9c4000x7f07d2e35a80655361925202465704812076535757787324120765357579678901207653575822612912076535758293045
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00809314819314864194304256002424445440x7f0902d9c3000x7f07d2e35ac01310722442083119086412076535758317170120765357584971681207653575862500712076535758628338
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00829314819314864194304256002424457600x7f0902d9ca000x7f07d2e35b001310722458703158586412076535758676478120765357588450071207653575897700612076535758980343
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00849314819314864194304256002424467200x7f0902d9c9000x7f07d2e35b401310722492943193130412076535759043641120765357592026051207653575933316512076535759336766
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00869314819314864194304256002824484480x7f0902d9c8000x7f07d2e35b801310722062182631932812076535759378744120765357595504441207653575981044312076535759877041
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00889314819314864194304256002824494080x7f0902d9c7000x7f07d2e35bc0655361705002182367212076535759900815120765357600838821207653576033764212076535760406656
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00909314819314864194304256002424503680x7f0902d9c6000x7f07d2e35c001310722515823225937612076535760434698120765357606096411207653576074004012076535760743443
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00929314819314864194304256002424515840x7f0902d9c5000x7f07d2e35c401310722492703189314412076535760792654120765357609614801207653576110291912076535761106789
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00949314819314864194304256002424525440x7f0902d9c4000x7f07d2e35c801310722469763158148012076535761169635120765357613317181207653576146451812076535761468201
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00969314819314864194304256002824542720x7f0902d9c3000x7f07d2e35cc01310722161902766452012076535761516901120765357616833971207653576194467612076535762016901
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00989314819314864194304256002824554880x7f0902d9ca000x7f07d2e35d00655361791782295342412076535762042028120765357622222751207653576247827412076535762546216
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001009314819314864194304256002424567040x7f0902d9c9000x7f07d2e35d401310722688483430283212076535762572715120765357627467541207653576287635312076535762879887
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001029314819314864194304256002424581760x7f0902d9c8000x7f07d2e35d801310722540663250544012076535762930821120765357630982721207653576324211212076535763245797
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001049314819314864194304256002424593920x7f0902d9c7000x7f07d2e35dc01310722544643249854412076535763306641120765357634661111207653576363859112076535763642585
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001069314819314864194304256002824613760x7f0902d9c6000x7f07d2e35e001310722474003193220012076535763691106120765357638566701207653576411698912076535764185105
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001089314819314864194304256002824625920x7f0902d9c5000x7f07d2e35e40655361747522235953612076535764212716120765357643875481207653576464562712076535764713207
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001109314819314864194304256002424638080x7f0902d9c4000x7f07d2e35e801310722541163256062412076535764738193120765357649179461207653576504722612076535765050965
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001129314819314864194304256002424652800x7f0902d9c3000x7f07d2e35ec01310722654283413068812076535765101499120765357652726651207653576540914512076535765412748
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001149314819314864194304256002424664960x7f0902d9ca000x7f07d2e35f001310722517603213097612076535765472980120765357656317041207653576576514312076535765768740
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001169314819314864194304256002824684800x7f0902d9c9000x7f07d2e35f401310722666303421016812076535765818683120765357659761831207653576624306212076535766292695
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001189314819314864194304256002824696960x7f0902d9c8000x7f07d2e35f80655361761142251985612076535766317060120765357664958611207653576675090012076535766797213
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001209314819314864194304256002424709120x7f0902d9c7000x7f07d2e35fc01310722539383230135212076535766824304120765357669972991207653576713025912076535767134280
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001229314819314864194304256002424723840x7f0902d9c6000x7f07d2e360001310722449263143905612076535767183742120765357673521781207653576749297812076535767496554
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001249314819314864194304256002424736000x7f0902d9c5000x7f07d2e360401310722502003196776812076535767557167120765357677132971207653576785297612076535767856544
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001269314819314864194304256002824758400x7f0902d9c4000x7f07d2e360801310722094602656663212076535767905485120765357680766561207653576834865512076535768398963
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001289314819314864194304256002824770560x7f0902d9c3000x7f07d2e360c0655361727082203610412076535768424510120765357686060941207653576890241312076535768924801
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001309314819314864194304256002424782720x7f0902d9ca000x7f07d2e361001310722488063181620812076535768968202120765357691339321207653576926721212076535769270795
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001329314819314864194304256002424800000x7f0902d9c9000x7f07d2e361401310722115762717349612076535769319635120765357694880111207653576963265012076535769636184
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001349314819314864194304256002424812160x7f0902d9c8000x7f07d2e361801310722482483174361612076535769699171120765357698552101207653576998752912076535769991145
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001369314819314864194304256002824834560x7f0902d9c7000x7f07d2e361c01310722053082639636812076535770040116120765357702065681207653577047552812076535770525308
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001389314819314864194304256002824849280x7f0902d9c6000x7f07d2e36200655362001502571453612076535770550705120765357707273671207653577097760612076535770999831
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001409314819314864194304256002424864000x7f0902d9c5000x7f07d2e362401310722590243323767212076535771048461120765357712113651207653577135008512076535771353869
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001429314819314864194304256002424881280x7f0902d9c4000x7f07d2e362801310722104882681610412076535771397080120765357715686441207653577171936312076535771722996
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001449314819314864194304256002424896000x7f0902d9c3000x7f07d2e362c01310722553263259698412076535771799488120765357719582431207653577209552212076535772099486
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001469314819314864194304256002824920960x7f0902d9ca000x7f07d2e363001310722216462831601612076535772149519120765357723177611207653577258480012076535772634592
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001489314819314864194304256002824935680x7f0902d9c9000x7f07d2e36340655361805562301532812076535772661191120765357728348801207653577309007912076535773141284
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001509314819314864194304256002424950400x7f0902d9c8000x7f07d2e363801310722527643249686412076535773169266120765357733430381207653577348207712076535773485645
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001529314819314864194304256002424967680x7f0902d9c7000x7f07d2e363c01310722567183264229612076535773533604120765357736988771207653577385695612076535773860472
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001549314819314864194304256002424982400x7f0902d9c6000x7f07d2e364001310722479283164815212076535773921786120765357740873551207653577422335512076535774227054
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015693148193148641943042560028241007360x7f0902d9c5000x7f07d2e364401310722007302561638412076535774278299120765357744670341207653577473535312076535774760516
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015893148193148641943042560028241022080x7f0902d9c4000x7f07d2e36480655361818722323784812076535774807073120765357749660721207653577522143212076535775249375
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016093148193148641943042560024241036800x7f0902d9c3000x7f07d2e364c01310722500403210549612076535775294149120765357754780711207653577561151012076535775614986
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016293148193148641943042560024241056640x7f0902d9ca000x7f07d2e365001310722503523209335212076535775662674120765357758559891207653577602286912076535776026661
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016493148193148641943042560024241071360x7f0902d9c9000x7f07d2e365401310722479163148733612076535776093175120765357762599881207653577639598812076535776399645
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016693148193148641943042560028241098880x7f0902d9c8000x7f07d2e365801310722129902729015212076535776443316120765357766187071207653577688734612076535776912188
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016893148193148641943042560028241113600x7f0902d9c7000x7f07d2e365c0655361743402240420812076535776956621120765357771276651207653577738558412076535777413762
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017093148193148641943042560024241128320x7f0902d9c6000x7f07d2e366001310722403723086812012076535777458324120765357776215841207653577775182312076535777755708
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017293148193148641943042560024241148160x7f0902d9c5000x7f07d2e366401310722488063167816812076535777807083120765357779673421207653577814142212076535778145182
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017493148193148641943042560024241162880x7f0902d9c4000x7f07d2e366801310722502783189432812076535778211245120765357783764611207653577851214112076535778515781
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017693148193148641943042560028241190400x7f0902d9c3000x7f07d2e366c01310721966542518053612076535778565193120765357787361401207653577899981912076535779026311
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017893148193148641943042560028241207680x7f0902d9ca000x7f07d2e36700655361724242213385612076535779069071120765357792297381207653577949261712076535779516673
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018093148193148641943042560024241224960x7f0902d9c9000x7f07d2e367401310722495603208097612076535779560214120765357797228561207653577986429612076535779868117
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018293148193148641943042560024241247360x7f0902d9c8000x7f07d2e367801310722586963287934412076535779922268120765357800940551207653578027773512076535780281726
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018493148193148641943042560024241264640x7f0902d9c7000x7f07d2e367c01310722524983205528012076535780342159120765357805023741207653578064141312076535780645062
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018693148193148641943042560020241279360x7f0902d9c6000x7f07d2e368001310722461483151455212076535780696878120765357808602931207653578112653212076535781155682
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018893148193148641943042560028241296640x7f0902d9c5000x7f07d2e36840655361779022276952812076535781197109120765357813590111207653578161309012076535781637819
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019093148193148641943042560024241313920x7f0902d9c4000x7f07d2e368801310722523963236407212076535781680769120765357818402891207653578197484912076535781978553
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019293148193148641943042560024241336320x7f0902d9c3000x7f07d2e368c01310722547923253531212076535782034837120765357822126081207653578240492712076535782433028
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019493148193148641943042560024241353600x7f0902d9ca000x7f07d2e369001310722483663179355212076535782487429120765357826522871207653578279148612076535782795262
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019693148193148641943042560020241368320x7f0902d9c9000x7f07d2e369401310722449723132220012076535782845636120765357830290851207653578331356412076535783340496
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019893148193148641943042560028241385600x7f0902d9c8000x7f07d2e36980655361901242437652812076535783377775120765357835532441207653578381036312076535783831048
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020093148193148641943042560024241402880x7f0902d9c7000x7f07d2e369c01310722411703106052812076535783875952120765357840434821207653578417820212076535784181981
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020293148193148641943042560024241427840x7f0902d9c6000x7f07d2e36a001310722478283162277612076535784230381120765357844026811207653578461404012076535784638470
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020493148193148641943042560024241447680x7f0902d9c5000x7f07d2e36a401310722349522993967212076535784701257120765357848642791207653578500187912076535785006485
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020693148193148641943042560020241457280x7f0902d9c4000x7f07d2e36a801310722546043274776812076535785055386120765357852297181207653578553835712076535785564312
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020893148193148641943042560028241477120x7f0902d9c3000x7f07d2e36ac0655361757562248039212076535785607042120765357857674761207653578602683512076535786052110
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021093148193148641943042560024241496960x7f0902d9ca000x7f07d2e36b001310722508583229317612076535786103586120765357862695551207653578640859412076535786412410
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021293148193148641943042560024241521920x7f0902d9c9000x7f07d2e36b401310722532183226985612076535786461531120765357866234731207653578685211312076535786876423
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021493148193148641943042560024241541760x7f0902d9c8000x7f07d2e36b801310722541683238592012076535786933600120765357871090721207653578724475112076535787248535
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021693148193148641943042560020241556480x7f0902d9c7000x7f07d2e36bc01310722494523210309612076535787297787120765357874761101207653578780618912076535787826761
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021893148193148641943042560028241576320x7f0902d9c6000x7f07d2e36c00655361871082398192812076535787871374120765357880404291207653578830426812076535788331029
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022093148193148641943042560024241596160x7f0902d9c5000x7f07d2e36c401310722473503161932812076535788375071120765357885380271207653578868234612076535788686220
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022293148193148641943042560024241623680x7f0902d9c4000x7f07d2e36c801310722467003163410412076535788737034120765357888993061207653578914650512076535789174738
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022493148193148641943042560024241646080x7f0902d9c3000x7f07d2e36cc01310722475783162044012076535789226074120765357893922641207653578953386412076535789537593
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022693148193148641943042560020241663360x7f0902d9ca000x7f07d2e36d001310722533983252968812076535789585973120765357897613451207653579013814512076535790168056
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022893148193148641943042560028241685760x7f0902d9c9000x7f07d2e36d40655361741942227464012076535790209373120765357903738231207653579063798212076535790660943
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023093148193148641943042560024241708160x7f0902d9c8000x7f07d2e36d801310722444743126097612076535790709183120765357908703021207653579100742212076535791010253
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023293148193148641943042560024241740800x7f0902d9c7000x7f07d2e36dc01310722452463151179212076535791060015120765357912301411207653579151126112076535791535720
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023493148193148641943042560024241765760x7f0902d9c6000x7f07d2e36e001310722722023469268812076535791586184120765357917458201207653579188598012076535791888607
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023693148193148641943042560020241777920x7f0902d9c5000x7f07d2e36e401310722482483169831212076535791939060120765357921150991207653579254213812076535792568141
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023893148193148641943042560028241802880x7f0902d9c4000x7f07d2e36e80655361865922389205612076535792610319120765357927680581207653579303093712076535793055427
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024093148193148641943042560024241827840x7f0902d9c3000x7f07d2e36ec01310722504863191220012076535793104528120765357932698171207653579340725612076535793410157
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024293148193148641943042560024241863040x7f0902d9ca000x7f07d2e36f001310722686343452544812076535793458437120765357936264561207653579394309512076535793966161
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024493148193148641943042560024241893120x7f0902d9c9000x7f07d2e36f401310722528223241075212076535794030641120765357941918951207653579434501412076535794347881
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024693148193148641943042560020241907840x7f0902d9c8000x7f07d2e36f801310722472203144180812076535794395910120765357945734941207653579509365312076535795117893
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024893148193148641943042560028241937920x7f0902d9c7000x7f07d2e36fc0655361736262217813612076535795170702120765357953349321207653579563317112076535795656455
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025093148193148641943042560024241968000x7f0902d9c6000x7f07d2e370001310722467803146032812076535795709153120765357958720511207653579602677112076535796029710
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025293148193148641943042560024242010880x7f0902d9c5000x7f07d2e370401310722290862921737612076535796081105120765357962634101207653579665012912076535796675861
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025493148193148641943042560024242046080x7f0902d9c4000x7f07d2e370801310722559603267665612076535796731535120765357968934891207653579707092812076535797073922
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025693148193148641943042560020242060800x7f0902d9c3000x7f07d2e370c01310722441943150332012076535797124085120765357972920481207653579791604612076535797939592
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025893148193148641943042560028242096000x7f0902d9ca000x7f07d2e37100655361840722364543212076535797983404120765357981477261207653579847748512076535798502169
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026093148193148641943042560024242131200x7f0902d9c9000x7f07d2e371401310722712823474334412076535798545679120765357987013251207653579888052412076535798883448
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026293148193148641943042560024242181760x7f0902d9c8000x7f07d2e371801310722424703123094412076535798932739120765357991032441207653579958084312076535799609268
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026493148193148641943042560024242222080x7f0902d9c7000x7f07d2e371c01310722472323170614412076535799664541120765357998274021207653580002788212076535800053374
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026693148193148641943042560020242239360x7f0902d9c6000x7f07d2e372001310722403823090293612076535800093789120765358002538011207653580095924012076535800985197
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026893148193148641943042560028242279680x7f0902d9c5000x7f07d2e37240655361726642212021612076535801034138120765358011926791207653580156675812076535801592497
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027093148193148641943042560024242320000x7f0902d9c4000x7f07d2e372801310722478303175813612076535801642821120765358018033981207653580200723712076535802032135
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027293148193148641943042560024242378240x7f0902d9c3000x7f07d2e372c01310722760443537679212076535802077709120765358022353971207653580278019612076535802805994
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027493148193148641943042560024242423680x7f0902d9ca000x7f07d2e373001310722450043141649612076535802860706120765358030301151207653580325443512076535803281779
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027693148193148641943042560020242435840x7f0902d9c9000x7f07d2e373401310722481523149934412076535803322906120765358034824341207653580428403212076535804311384
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027893148193148641943042560028242481280x7f0902d9c8000x7f07d2e37380655361923562455598412076535804358011120765358045337921207653580497955112076535805009192
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028093148193148641943042560024242526720x7f0902d9c7000x7f07d2e373c01310722654463399133612076535805056100120765358052160301207653580547843012076535805504694
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028293148193148641943042560024242592640x7f0902d9c6000x7f07d2e374001310722281802932059212076535805552934120765358057142691207653580632546812076535806355006
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028493148193148641943042560024242648320x7f0902d9c5000x7f07d2e374401310722511983215350412076535806411711120765358065728271207653580684258712076535806863562
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028693148193148641943042560020242663040x7f0902d9c4000x7f07d2e374801310722527463214620812076535806908185120765358070750661207653580806370412076535808133644
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028893148193148641943042560028242718720x7f0902d9c3000x7f07d2e374c0655361731062235880012076535808164101120765358083467431207653580886498212076535808933211
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029093148193148641943042560024242774400x7f0902d9ca000x7f07d2e375001310722448003128619212076535808962646120765358091477021207653580942226112076535809491410
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029293148193148641943042560012242799360x7f0902d9c9000x7f07d2e375401310722596003328086412076535809521185120765358096941001207653581043473912076535810503583
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029493148193148641943042560024242865280x7f0902d9c8000x7f07d2e375801310722444263125864812076535810545681120765358107080181207653581102593812076535811094492
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029693148193148641943042560020242880000x7f0902d9c7000x7f07d2e375c01310722456323145332012076535811124578120765358113027371207653581247793412076535812546192
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029893148193148641943042560032242945920x7f0902d9c6000x7f07d2e37600655361700462173128812076535812577931120765358127499341207653581336385212076535813431970
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030093148193148641943042560024243011840x7f0902d9c5000x7f07d2e376401310722487103176886412076535813463899120765358136369721207653581395745112076535814025394
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030293148193148641943042560012243049600x7f0902d9c4000x7f07d2e376801310722483583166913612076535814056531120765358142294501207653581510992912076535815178519
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030493148193148641943042560024243136000x7f0902d9c3000x7f07d2e376c01310722524163252436812076535815221809120765358153836881207653581581808712076535815885494
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030693148193148641943042560020243148160x7f0902d9ca000x7f07d2e377001310722640903353802412076535815916171120765358161072061207653581766064312076535817730826
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030893148193148641943042560020243175680x7f0902d9c9000x7f07d2e37740655361774062259721612076535817763046120765358179451221207653581874400112076535818812649
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031093148193148641943042560012243203200x7f0902d9c8000x7f07d2e377801310722507103186975212076535818840731120765358190308801207653581946991912076535819536936
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031293148193148641943042560012243240960x7f0902d9c7000x7f07d2e377c01310722552983258463212076535819563996120765358197407981207653582090127612076535820969440
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031493148193148641943042560012243288960x7f0902d9c6000x7f07d2e378001310722482163169914412076535821012781120765358211745551207653582196111312076535822030574
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031693148193148641943042560020243301120x7f0902d9c5000x7f07d2e378401310722322082989011212076535822062013120765358222345531207653582529326612076535825360979
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031893148193148641943042560020243328640x7f0902d9c4000x7f07d2e37880655362059802638108012076535825392768120765358255702251207653582711982212076535827188138
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032093148193148641943042560012243356160x7f0902d9c3000x7f07d2e378c01310722539683233687212076535827218074120765358273990211207653582818990012076535828258429
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032293148193148641943042560012243393920x7f0902d9ca000x7f07d2e379001310722450343158221612076535828289777120765358284750191207653583075965412076535830828349
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032493148193148641943042560012243441920x7f0902d9c9000x7f07d2e379401310722469903147057612076535830872331120765358310430131207653583258013012076535832649998
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032693148193148641943042560020243454080x7f0902d9c8000x7f07d2e379801310722484983168212012076535832681005120765358328631691207653583892635612076535838998787
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032893148193148641943042560020243481600x7f0902d9c7000x7f07d2e379c0655361648362112050412076535839030656120765358392148351207653584226138912076535842334422
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033093148193148641943042560012243509120x7f0902d9c6000x7f07d2e37a001310722691783462367212076535842363666120765358425466681207653584408714512076535844155389
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332931481931486419430425600122400x7f0902d9c5000x7f07d2e37a401310722295842952856012076535844185946120765358443639441207653584889369412076535848961960